© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5157
    Prev
    Next
    INDEX
    Explanations

    Alaska, Arctic, Inuit culture

    np_acts-logits-general · gemini-2.5-flash-lite

    Arctic, Alaska, North Pole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phường
    0.54
     Cincinnati
    0.52
    颜值
    0.48
     زین
    0.48
     সাজেশন
    0.48
     आवृत्ति
    0.48
    缙
    0.48
     لاہور
    0.47
    饴
    0.47
     एपिस
    0.46
    POSITIVE LOGITS
    Alaska
    1.30
     Alaska
    1.29
     Inuit
    1.27
     Arctic
    1.26
     tundra
    1.24
    Arctic
    1.22
     Alaskan
    1.20
     arctic
    1.19
     Yukon
    1.02
     Greenland
    0.96
    Activations Density 0.111%

    No Known Activations